diff options
author | Guillaume Klein <guillaume.klein@systrangroup.com> | 2022-01-11 14:37:30 +0300 |
---|---|---|
committer | Guillaume Klein <guillaume.klein@systrangroup.com> | 2022-01-11 14:37:30 +0300 |
commit | b856a8bcd151dea52f4f01e0090f03c1a4daf1b5 (patch) | |
tree | a7e599849dc04f1d812a57c8c43957146cb39bcf | |
parent | da024e56b45a804b4391222c00d2c60ab13f042d (diff) |
Bump version to 2.11.0v2.11.0
-rw-r--r-- | CHANGELOG.md | 20 | ||||
-rw-r--r-- | python/ctranslate2/version.py | 2 |
2 files changed, 21 insertions, 1 deletions
diff --git a/CHANGELOG.md b/CHANGELOG.md index 035df40c..d6df08ab 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -4,6 +4,26 @@ ### Fixes and improvements +## [v2.11.0](https://github.com/OpenNMT/CTranslate2/releases/tag/v2.11.0) (2022-01-11) + +### Changes + +* With CUDA >= 11.2, the environment variable `CT2_CUDA_ALLOCATOR` now defaults to `cuda_malloc_async` which should improve performance on GPU. + +### New features + +* Build Python wheels for AArch64 Linux + +### Fixes and improvements + +* Improve performance of Gather CUDA kernel by using vectorized copy +* Update Intel oneAPI to 2022.1 +* Update oneDNN to 2.5.1 +* Log some additional information with `CT2_VERBOSE` >= 1: + * Location and compute type of loaded models + * Version of the dynamically loaded cuBLAS library + * Selected CUDA memory allocator + ## [v2.10.1](https://github.com/OpenNMT/CTranslate2/releases/tag/v2.10.1) (2021-12-15) ### Fixes and improvements diff --git a/python/ctranslate2/version.py b/python/ctranslate2/version.py index bcedf03d..1015c5d5 100644 --- a/python/ctranslate2/version.py +++ b/python/ctranslate2/version.py @@ -1,3 +1,3 @@ """Version information.""" -__version__ = "2.10.1" +__version__ = "2.11.0" |